58 citations · 92 across the 11 of their papers we have counts for
10 papers
Causal Transportability for Visual Recognition
Chengzhi Mao, Kevin Xia, James Wang +4
Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features. Our main observation is that image classifiers may perform poo…
A Tale of Two Models: Constructing Evasive Attacks on Edge Models
Wei Hao, Aahil Awatramani, Jiayang Hu +5
Full-precision deep learning models are typically too large or costly to deploy on edge devices. To accommodate to the limited hardware resources, models are adapted to the edge us…
Using Multiple Self-Supervised Tasks Improves Model Robustness
Matthew Lawhon, Chengzhi Mao, Junfeng Yang
Deep networks achieve state-of-the-art performance on computer vision tasks, yet they fail under adversarial attacks that are imperceptible to humans. In this paper, we propose a n…
Adversarial Attacks are Reversible with Natural Supervision
Chengzhi Mao, Mia Chiquier, Hao Wang +2
We find that images contain intrinsic structure that enables the reversal of many adversarial attacks. Attack vectors cause not only image classifiers to fail, but also collaterall…
Generative Interventions for Causal Learning
Chengzhi Mao, Augustine Cha, Amogh Gupta +3
We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally…
Multitask Learning Strengthens Adversarial Robustness
Chengzhi Mao, Amogh Gupta, Vikram Nitin +4
Although deep networks achieve strong accuracy on a range of computer vision benchmarks, they remain vulnerable to adversarial attacks, where imperceptible input perturbations fool…